Skip to content
AgentProv

2026-10-13 · 2026-Q4

Anthropic: Small Open-Weight Models Are Close to Self-Replicating Across Cheap IoT Devices

Outside the model: AI capabilityAgent tooling was not the attack surface, so no layer applies.

Fixable
Architectural
Vendor response
Unknown
In the wild
No
Actor
Not applicable

Target

Consumer IoT devices with unauthenticated ADB access, tested on emulated networks and 15 off-brand Android TV boxes

Impact

Anthropic's Frontier Red Team tested 11 open-weight models. GLM-5.2 propagated Llama3.1-8B to all 8 nodes of an emulated network in 4 of 5 trials, Qwen3.5-9B set up inference on 8 of 9 hardware types (45% success, 84% when earlier attempts were retained), and Gemma4-26B was split across 15 TV boxes at 0.39 tokens per second. Anthropic estimates models of 30B parameters or fewer could reach the full capability by the end of 2026 and found no working replicator in the wild. Research, not an incident

Root cause

Large fleets of cheap devices with exposed debug interfaces provide compute and spread paths for a model able to chain the steps itself

Sources

Catalog

Cite this: AgentProv incident record: Anthropic: Small Open-Weight Models Are Close to Self-Replicating Across Cheap IoT Devices (2026-10-13). https://agentprov.com/incidents/2026-10-13-anthropic-small-open-weight-models-are-close-to-self-replicating-across-cheap